A Comparison of Audio Signal Preprocessing Methods for Deep Neural Networks on Music Tagging
Sound
2021-02-23 v3 Computer Vision and Pattern Recognition
Information Retrieval
Machine Learning
Abstract
In this paper, we empirically investigate the effect of audio preprocessing on music tagging with deep neural networks. We perform comprehensive experiments involving audio preprocessing using different time-frequency representations, logarithmic magnitude compression, frequency weighting, and scaling. We show that many commonly used input preprocessing techniques are redundant except magnitude compression.
Keywords
Cite
@article{arxiv.1709.01922,
title = {A Comparison of Audio Signal Preprocessing Methods for Deep Neural Networks on Music Tagging},
author = {Keunwoo Choi and György Fazekas and Kyunghyun Cho and Mark Sandler},
journal= {arXiv preprint arXiv:1709.01922},
year = {2021}
}
Comments
5 pages. EUSIPCO 2018 camera-ready. arXiv:1706.02361 does not have the overlapped part with this submission anymore